dev

A command that opens MCP Inspector for debugging a plugin. MCP Inspector is a local web interface for viewing and trying the plugin's available tools and other published interface items.

In plain words
What is it for?
Use it to open the inspector locally, review tools, resources, templates, and prompts, call tools with test arguments, and inspect schemas and returned data.
Why use it?
It gives developers a place to inspect tool inputs and outputs and test calls without using Claude. This makes it easier to find problems in the plugin's MCP integration.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/uri6407/claudegram/dev
Clone the repo
git clone --depth 1 https://github.com/Uri6407/claudegram
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 167 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00167
Opus 5 $0.00008 $0.00084
Sonnet 5 $0.00003 $0.00033
Haiku 4.5 $0.00002 $0.00017

Measured yesterday against content hash 9bf931d53723, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to dev — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/dev.md · 20 lines

What it actually says

Подними MCP Inspector с подключённым Claudegram-сервером:

! claudegram-dev

Inspector откроется на http://localhost:6274. Сможешь:

  • Видеть все 120 tools / 9 resources / 6 templates / 7 prompts.
  • Вызывать любой tool с произвольными аргументами.
  • Смотреть outputSchema и structuredContent.
  • Тестировать completion и prompts.

Channel-режим и permission-relay в Inspector не работают — это лимитация mcp dev (запускает наш mcp объект напрямую, в обход кастомного _run_async).

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 20 lines · 15 tokens per session scan A 9bf931d53723

Subscribe to this mod's changes

dev is a command published in the GitHub repository Uri6407/claudegram (2 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 167 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to dev, differing in 0 lines, and is treated as a copy.